Day1 Data Visualization using Matplotlib.ipynb

Kernel: Python 3 (ipykernel)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Generating sample data
np.random.seed(0)
data = {
    'Technology': np.random.choice(['Python', 'Java', 'JavaScript', 'C++', 'Ruby'], 3000),
    'Usage': np.random.randint(1, 11, 3000),
    'Popularity': np.random.randint(1, 101, 3000),
    'Cost': np.random.uniform(100, 1000, 3000),
    'Innovation': np.random.randint(1, 6, 3000)
}
df = pd.DataFrame(data)

# Example plots
# Histogram
plt.figure(figsize=(8, 6))
plt.hist(df['Usage'], bins=20, color='skyblue', edgecolor='black')
plt.title('Usage Distribution')
plt.xlabel('Usage')
plt.ylabel('Frequency')
plt.grid(True)
plt.show()

# Scatter plot
plt.figure(figsize=(8, 6))
plt.scatter(df['Popularity'], df['Cost'], color='orange', alpha=0.5)
plt.title('Popularity vs Cost')
plt.xlabel('Popularity')
plt.ylabel('Cost')
plt.grid(True)
plt.show()

# Bar plot
tech_counts = df['Technology'].value_counts()
plt.figure(figsize=(10, 6))
plt.bar(tech_counts.index, tech_counts.values, color='green')
plt.title('Technology Distribution')
plt.xlabel('Technology')
plt.ylabel('Count')
plt.xticks(rotation=45)
plt.grid(axis='y')
plt.show()

# Box plot
plt.figure(figsize=(8, 6))
plt.boxplot(df['Innovation'], vert=False)
plt.title('Innovation Distribution')
plt.xlabel('Innovation')
plt.grid(True)
plt.show()

# Line chart
plt.figure(figsize=(10, 6))
tech_usage_mean = df.groupby('Technology')['Usage'].mean()
plt.plot(tech_usage_mean.index, tech_usage_mean.values, marker='o', linestyle='-')
plt.title('Average Usage of Technologies')
plt.xlabel('Technology')
plt.ylabel('Average Usage')
plt.xticks(rotation=45)
plt.grid(True)
plt.show()

## pip install wordcloud --trusted-host pypi.org --trusted-host files.pythonhosted.org